AI RESEARCH
A Survey of Scaling in Large Language Model Reasoning
arXiv CS.AI
•
ArXi:2504.02181v2 Announce Type: replace The rapid advancements in large Language models (LLMs) have significantly enhanced their reasoning capabilities, driven by various strategies such as multi-agent collaboration. However, unlike the well-established performance improvements achieved through scaling data and model size, the scaling of reasoning in LLMs is complex and can even negatively impact reasoning performance,